Jan

Jan is a privacy-focused, open-source ChatGPT alternative that runs locally. It supports connecting to cloud providers like TensorX through OpenAI-compatible configuration.

Prerequisites

• Jan installed from jan.ai

• TensorX API key from app.tensorx.ai

Configuration

Step 1: Open Settings

1. Click Settings in the bottom-left corner of Jan

2. Navigate to Model Providers in the left sidebar

Step 2: Configure OpenAI Provider

1. Select OpenAI from the Model Providers list

2. Enter your TensorX credentials:

   • API Key: Your TensorX API key

   • API Base URL: https://api.tensorx.ai/v1

3. Click Save

Step 3: Add TensorX Models

To add a TensorX model:

1. Go to Settings > Model Providers > OpenAI

2. Call GET /v1/models and add one of the returned IDs.

Using Models in Chat

1. Open a new chat or existing thread

2. Click the model selector dropdown

3. Choose your configured TensorX model

4. Start a chat.

Manual Model Configuration

For advanced users, you can manually add models via JSON configuration:

1. Navigate to Jan Data Folder:

   • Mac: ~/Library/Application Support/jan/models/

   • Windows: %APPDATA%\jan\models\

   • Linux: ~/.config/jan/models/

2. Create a new folder for your model (for example, tensorx-model)

3. Create a model.json file:

{
  "id": "<MODEL_ID>",
  "object": "model",
  "name": "TensorX model",
  "description": "Model served through the TensorX API",
  "parameters": {
    "temperature": 0.7,
    "top_p": 0.95,
    "stream": true
  },
  "metadata": {
    "author": "TensorX",
    "tags": ["TensorX"]
  },
  "engine": "openai"
}

Replace <MODEL_ID> with an ID returned by GET /v1/models.

Model selection

Call GET /v1/models with your TensorX API key and use one of the returned IDs. If the integration depends on a capability or token limit, query GET /v1/model/info before selecting the model. See Models for examples.

---

Troubleshooting

Model not connecting

1. Verify API key is entered correctly

2. Ensure base URL is https://api.tensorx.ai/v1 (with /v1)

3. Check Jan's logs for error details

Model unavailable

• Confirm the model ID matches exactly (case-sensitive)

• Verify your TensorX account has access to the model

Slow responses

• Check your network connection and the request latency in the TensorX usage dashboard.

Resources

• Jan Documentation

• Jan GitHub

• TensorX API Reference